Image Correction Method and Image Correction Apparatus

1. An image correction method, comprising: identifying each pixel in an image as one of a foreground pixel and a background pixel; estimating a brightness of a background corresponding to a foreground pixel based on the brightness and a gradient of the brightness of background pixels adjacent to the foreground pixel to fill the background located in a position of the foreground pixel to obtain a background illumination map of the image according to filled backgrounds along with background pixels; and correcting the image based on the brightness of each pixel in the image and the background illumination map, wherein the estimating the brightness of the background corresponding to the foreground pixel includes, determining background pixels with an effective gradient among the background pixels adjacent to the foreground pixel; for each one of the determined background pixels with the effective gradient, calculating, based on the brightness and the gradient of the brightness of the background pixel, an estimated value of the brightness of the background corresponding to the foreground pixel; and obtaining the brightness of the background corresponding to the foreground pixel by averaging estimated values calculated for each one of the determined background pixels, wherein each one of the background pixels with the effective gradient is a pixel in a connection direction from the foreground pixel to the pixel, pixels adjacent to the pixel are background pixels.

2. The image correction method according to claim 1 , wherein the identifying is performed based on the gradient of the brightness and color saturation of the pixel in the image.

3. The image correction method according to claim 1 , further comprising estimating a natural illumination intensity based on the brightness of the background pixels in the image.

4. The image correction method according to claim 3 , wherein the natural illumination intensity is estimated based on a mean value of the brightness of the background pixels in the image.

5. The image correction method according to claim 3 , wherein in the correcting, in addition to the brightness of each pixel in the image and the background illumination map, the image is corrected based on the natural illumination intensity.

6. The image correction method according to claim 1 , wherein in the identifying, expansion processing is performed on the foreground pixel.

7. The image correction method according to claim 1 , wherein in the estimating the brightness of the background, the background illumination map of the image is obtained by an iteration process by taking the filled background as the background pixel.

8. The image correction method according to claim 1 , wherein in the estimating the brightness of the background, the obtained background illumination map is smoothed.

9. An image correction apparatus, comprising: a processor configured to: identify each pixel in an image as one of a foreground pixel and a background pixel; estimate a brightness of a background corresponding to a foreground pixel based on the brightness and a gradient of the brightness of background pixels adjacent to the foreground pixel to fill the background located in a position of the foreground pixel to obtain a background illumination map of the image according to filled backgrounds along with background pixels; and correct the image based on the brightness of each pixel in the image and the background illumination map, wherein the brightness of the background corresponding to the foreground pixel is estimated by: determining background pixels with an effective gradient among the background pixels adjacent to the foreground pixel; for each one of the determined background pixels with the effective gradient, calculating, based on the brightness and the gradient of the brightness of the background pixel, an estimated value of the brightness of the background corresponding to the foreground pixel; and obtaining the brightness of the background corresponding to the foreground pixel by averaging estimated values calculated for each one of the determined background pixels, wherein each one of the background pixels with the effective gradient is a pixel in a connection direction from the foreground pixel to the pixel, pixels adjacent to the pixel are background pixels.

10. The image correction apparatus according to claim 9 , wherein the identifying is performed based on the gradient of the brightness and color saturation of the pixel in the image.

11. The image correction apparatus according to claim 9 , wherein the processor further configured to estimate a natural illumination intensity based on the brightness of the background pixels in the image.

12. The image correction apparatus according to claim 11 , wherein the natural illumination intensity is estimated based on a mean value of the brightness of the background pixels in the image.

13. The image correction apparatus according to claim 11 , wherein in addition to the brightness of each pixel in the image and the background illumination map, the image is corrected based on the natural illumination intensity.

14. The image correction apparatus according to claim 9 , wherein an expansion processing is performed on the foreground pixel.

15. The image correction apparatus according to claim 9 , wherein the background illumination map of the image is obtained by an iteration process by taking the filled background as the background pixel.

16. The image correction apparatus according to claim 9 , wherein the obtained background illumination map is smoothed.

17. A non-transitory computer readable storage medium having recorded thereon a program, which when executed by a computer, causes the computer to execute a method, the method comprising: identifying each pixel in an image as one of a foreground pixel and a background pixel; estimating a brightness of a background corresponding to a foreground pixel based on the brightness and a gradient of the brightness of background pixels adjacent to the foreground pixel to fill the background located in a position of the foreground pixel to obtain a background illumination map of the image according to filled backgrounds along with background pixels; and correcting the image based on the brightness of each pixel in the image and the background illumination map, wherein the estimating the brightness of the background corresponding to the foreground pixel includes, determining background pixels with an effective gradient among the background pixels adjacent to the foreground pixel; for each one of the determined background pixels with the effective gradient, calculating, based on the brightness and the gradient of the brightness of the background pixel, an estimated value of the brightness of the background corresponding to the foreground pixel; and obtaining the brightness of the background corresponding to the foreground pixel by averaging estimated values calculated for each one of the determined background pixels, wherein each one of the background pixels with the effective gradient is a pixel in a connection direction from the foreground pixel to the pixel, pixels adjacent to the pixel are background pixels.